© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28224
    Prev
    Next
    INDEX
    Explanations

    words that symbolize representation or exemplification of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    85
    +0.10
    0.5%
    726
    +0.10
    0.4%
    202
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    0.00
    555
    +0.10
    0.02
    167
    +0.10
    0.00
    Negative Logits
    ingly
    -0.71
    standing
    -0.71
     Remastered
    -0.65
    mpeg
    -0.64
    vor
    -0.60
    wards
    -0.60
     Fuller
    -0.58
    DonaldTrump
    -0.57
    ancing
    -0.57
    edu
    -0.56
    POSITIVE LOGITS
    helial
    0.94
    het
    0.83
    endor
    0.79
    axy
    0.73
    ablishment
    0.71
    hetical
    0.71
    ome
    0.70
    lights
    0.70
    hel
    0.69
    aurus
    0.67
    Activations Density 0.128%

    No Known Activations